Health degree diagnosis method of photovoltaic module

Abstract

The invention relates to the technical field of photovoltaic modules, in particular to a health degree diagnosis method of a photovoltaic module. Comprising the following steps: generating a plurality of characteristic indexes according to photovoltaic module parameters, and establishing a standard model and an expected aging model; obtaining operation parameters of the photovoltaic module according to a preset feedback time node, and generating a monitoring data packet according to the operation parameters; generating a health evaluation value of the photovoltaic module according to the monitoring data packet, the standard model and the expected aging model, and judging whether an operation early warning instruction is generated or not according to the health evaluation value; extracting a plurality of characteristic indexes according to the historical operation parameters, generating a standard operation curve of each characteristic index according to the historical environment parameters, establishing a standard model, eliminating disturbance of the environment to the characteristic indexes, and correcting a real-time health evaluation value of the photovoltaic module according to the accumulated operation duration of the photovoltaic module and an expected aging model. Therefore, the health evaluation value can reflect the health state of the photovoltaic module more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic modules, and in particular to a method for diagnosing the health status of photovoltaic modules. Background Art

[0002] In recent years, the photovoltaic industry has developed rapidly, and the health of photovoltaic modules is the key to the long-term efficient, stable and safe operation of photovoltaic power generation systems. Generally, professionals conduct regular inspections, refer to relevant industry standards, personal experience and the actual operation of the modules, and judge the health of photovoltaic modules.

[0003] However, the photovoltaic system is an unstable and complex system during operation. Its output characteristics change with environmental factors such as light, photovoltaic module surface temperature, humidity, wind speed, etc. In addition, it is also affected by many factors such as the condition of system components. Only through personnel inspection, it is impossible to judge the operating status of photovoltaic modules in time, nor to warn of the failure risk of photovoltaic modules in time, which is not conducive to the stable operation of photovoltaic modules. Summary of the invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a method for diagnosing the health of photovoltaic modules, aiming to improve the diagnostic accuracy of the operating status of photovoltaic modules and realize real-time monitoring and fault warning of photovoltaic modules.

[0005] In some embodiments of the present application, multiple characteristic indicators are extracted based on historical operating parameters, and standard operating curves of each characteristic indicator are generated based on historical environmental parameters, and a standard model is established to eliminate environmental disturbances on the characteristic indicators, thereby improving the evaluation accuracy of the operating health status of photovoltaic components.

[0006] In some embodiments of the present application, by establishing an expected aging model, when a photovoltaic component is in an abnormal state, the real-time health evaluation value of the photovoltaic component is corrected according to the cumulative operating time of the photovoltaic component and the expected aging model, so as to determine whether the photovoltaic component has abnormal loss problems, so that the health evaluation value can more accurately reflect the health status of the photovoltaic component, and the failure risk of the photovoltaic component can be repaired in time to ensure the stable operation of the photovoltaic component and improve the service life of the photovoltaic component.

[0007] In some embodiments of the present application, a method for diagnosing the health of a photovoltaic module is provided, comprising:

[0008] Generate multiple characteristic indicators based on PV module parameters, and establish standard models and expected aging models;

[0009] Obtaining the operating parameters of the photovoltaic components according to the preset feedback time nodes, and generating a monitoring data packet according to the operating parameters;

[0010] Generate health evaluation values ​​of PV modules based on monitoring data packets, standard models and expected aging models, and determine whether to generate operation warning instructions based on the health evaluation values;

[0011] Among them, when generating multiple characteristic indicators, including:

[0012] Establish a characteristic index sequence A, A = (a1, a2...an), where ai is the i-th characteristic index and n is the number of characteristic indicators.

[0013] In some embodiments of the present application, when establishing a standard model and an expected aging model, the process includes:

[0014] Obtain historical operating parameters and historical environmental parameters of photovoltaic modules;

[0015] Select the target characteristic index according to the characteristic index sequence A;

[0016] Generate an initial standard operating range of target characteristic indicators based on historical operating parameters;

[0017] Generate environmental disturbance curves of target characteristic indicators based on historical environmental parameters;

[0018] Generate a standard operating curve of the target characteristic index according to the environmental disturbance curve and the initial standard operating range;

[0019] Establish a standard model based on the standard operating curves of all characteristic indicators;

[0020] Establishing a running timeline;

[0021] Generate an aging curve of target characteristic indicators based on the operation timeline and historical operation parameters;

[0022] According to the aging curves of all characteristic indicators, an expected aging model is established.

[0023] In some embodiments of the present application, when a monitoring data packet is generated according to an operating parameter, it includes:

[0024] Obtain the real-time operating parameters of the photovoltaic components at the current feedback time node;

[0025] Extract the operating reference value of each characteristic indicator and establish an operating reference value sequence B, B = (b1, b2...bn), where bi is the operating reference value of the i-th characteristic indicator at the current feedback time node;

[0026] Obtain the real-time environment parameters and accumulated running time of the current feedback time node according to the real-time running parameters;

[0027] Generate environmental index tags based on real-time environmental parameters;

[0028] Generate duration index tags based on the accumulated running time;

[0029] Generate a monitoring data packet of the current feedback time node according to the operating reference value series B, the environment index tag and the duration index tag.

[0030] In some embodiments of the present application, when generating the health evaluation value of a photovoltaic module, the process includes:

[0031] Generate standard reference values ​​for each characteristic index based on the environmental index tags in the monitoring data package and all standard operating curves;

[0032] Establish a standard reference value sequence C, C = (c1, c2...cn); where ci is the standard reference value of the i-th characteristic indicator at the current feedback time node;

[0033] Generate the deviation evaluation value h of the current feedback time node according to the standard model;

[0034]

[0035] Among them, Q1 is the preset first fixed coefficient, βi is the fluctuation correction coefficient of the i-th characteristic indicator; αi is the influencing factor of the i-th characteristic indicator;

[0036] The health evaluation value g of the current feedback time node is set according to the deviation evaluation value h.

[0037] In some embodiments of the present application, when setting the fluctuation correction coefficient βi, it includes:

[0038] Set evaluation cycle and target characteristic indicators;

[0039] Generate the first-level monitoring values ​​of the target characteristic indicators at each feedback time node in the current evaluation cycle based on historical monitoring data;

[0040] Correct all primary monitoring values ​​of target characteristic indicators in the current evaluation period according to the environmental disturbance curve;

[0041] Generate secondary monitoring values ​​for each feedback time node in the current evaluation cycle based on the correction results;

[0042] Establish the secondary monitoring value series F, F = (f 1 , f 2 …f m ), where m is the number of feedback time nodes in the current evaluation cycle; f i is the secondary monitoring value of the target characteristic indicator at the i-th feedback time node;

[0043] Generate the fluctuation evaluation value k of the target characteristic index according to the secondary monitoring value series F;

[0044] The fluctuation correction coefficient β of the target characteristic index is set according to the fluctuation evaluation value k.

[0045] In some embodiments of the present application, when generating a fluctuation evaluation value k of a target characteristic index, the method includes: k=e3*Q1* (f i -f') 2 ]+e4*Q2*[ (f i -f i-1 ) 2 ]; Among them, e3 is the preset third weight coefficient, e4 is the preset fourth weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; f' is the average value of all data in the secondary monitoring value series.

[0048] In some embodiments of the present application, when the health evaluation value g of the current feedback time node is set according to the deviation evaluation value h, it includes:

[0049] Presetting a first deviation evaluation value interval (H1, H2), a second deviation evaluation value interval (H2, H3) and a third deviation evaluation value interval (H3, H4);

[0050] If the deviation evaluation value h is within the preset first deviation evaluation value interval, the health evaluation value g=r / h is set, where r is the preset conversion coefficient;

[0051] If the deviation evaluation value h is within the preset second deviation evaluation value interval, a health evaluation value g is generated according to the expected aging model;

[0052] If the deviation evaluation value h is within the preset third deviation evaluation value interval, a first-level operation warning instruction is generated.

[0053] In some embodiments of the present application, when generating a health evaluation value g according to an expected aging model, the method includes:

[0054] Generate aging reference values ​​for each characteristic indicator based on the duration index tag and all aging curves in the monitoring data packet;

[0055] Establish an aging reference value sequence D, D = (d1, d2 ... dn), where di is the aging reference value of the i-th characteristic indicator at the current feedback time node;

[0056] The expected aging model generates a health assessment value g;

[0057]

[0058] Among them, e1 is the preset first weight coefficient, e2 is the preset second weight coefficient; αi is the influencing factor of the i-th characteristic indicator.

[0059] In some embodiments of the present application, when determining whether to generate an operation warning instruction according to the health evaluation value, it includes:

[0060] Preset a first health evaluation value interval (G1, G2), a second health evaluation value interval (G2, G3) and a third health evaluation value interval (G3, G4);

[0061] If the health evaluation value g is within the preset first health evaluation value interval, the current feedback time node generates a first-level operation warning instruction;

[0062] If the health evaluation value g is within the preset second health evaluation value interval, the current feedback time node generates a second-level operation warning instruction;

[0063] If the health evaluation value g is within the preset third health evaluation value interval, no operation warning instruction is generated at the current feedback time node.

[0064] Compared with the prior art, the method for diagnosing the health of a photovoltaic module in the embodiment of the present application has the following beneficial effects:

[0065] Multiple characteristic indicators are extracted based on historical operating parameters, and standard operating curves of various characteristic indicators are generated based on historical environmental parameters. A standard model is established to eliminate environmental disturbances on the characteristic indicators, thereby improving the accuracy of evaluating the health status of photovoltaic modules.

[0066] By establishing an expected aging model, when a PV module is in an abnormal state, the real-time health evaluation value of the PV module is corrected according to the cumulative operating time of the PV module and the expected aging model, so as to determine whether the PV module has abnormal loss problems. This allows the health evaluation value to more accurately reflect the health status of the PV module, and to promptly inspect and repair the failure risks of the PV module, thereby ensuring the stable operation of the PV module and increasing the service life of the PV module. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a flow chart of a method for diagnosing the health status of a photovoltaic module in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0068] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0069] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0070] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0071] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0072] like Figure 1 As shown, a method for diagnosing the health of a photovoltaic module according to a preferred embodiment of the present application includes:

[0073] S101: Generate multiple characteristic indicators according to photovoltaic module parameters, and establish a standard model and an expected aging model;

[0074] S102: acquiring operating parameters of the photovoltaic components according to a preset feedback time node, and generating a monitoring data packet according to the operating parameters;

[0075] S103: Generate a health evaluation value of the photovoltaic component according to the monitoring data packet, the standard model and the expected aging model, and determine whether to generate an operation warning instruction according to the health evaluation value;

[0076] Among them, when generating multiple characteristic indicators, including:

[0077] Establish a characteristic index sequence A, A = (a1, a2...an), where ai is the i-th characteristic index and n is the number of characteristic indicators.

[0078] Specifically, the characteristic indicators include but are not limited to: the internal temperature, current, voltage, output power of the photovoltaic module, the internal humidity of the photovoltaic module, parallel resistance, and other parameters. By preprocessing the historical operating parameters, various relevant characteristic indicators are extracted, and the operating status of the photovoltaic module is comprehensively evaluated based on multiple characteristic indicators.

[0079] Specifically, when establishing standard models and expected aging models, include:

[0080] Obtain historical operating parameters and historical environmental parameters of photovoltaic modules;

[0081] Select the target characteristic index according to the characteristic index sequence A;

[0082] Generate an initial standard operating range of target characteristic indicators based on historical operating parameters;

[0083] Generate environmental disturbance curves of target characteristic indicators based on historical environmental parameters;

[0084] Generate a standard operating curve of the target characteristic index according to the environmental disturbance curve and the initial standard operating range;

[0085] Establish a standard model based on the standard operating curves of all characteristic indicators;

[0086] Establishing a running timeline;

[0087] Generate an aging curve of target characteristic indicators based on the operation timeline and historical operation parameters;

[0088] According to the aging curves of all characteristic indicators, an expected aging model is established.

[0089] Specifically, multiple environmental index tags are generated according to historical environmental parameters. A single environmental index tag includes parameters such as environmental temperature, environmental humidity, and light intensity. Each environmental index tag corresponds to different environmental conditions.

[0090] Specifically, an environmental disturbance curve is constructed based on all environmental index tags, wherein the environmental index tags are coordinate points on the environmental disturbance curve. The standard operation curve of each characteristic index is constructed through the environmental disturbance curve, that is, the standard reference value corresponding to each characteristic index under different environmental conditions is constructed.

[0091] Specifically, by introducing the environmental disturbance curve, the standard reference value of each characteristic indicator is corrected to eliminate the impact of environmental disturbance on photovoltaic modules, avoid misjudgment of monitoring results due to short-term fluctuations in the operating parameters of photovoltaic modules caused by short-term environmental changes, and improve the evaluation accuracy of the health status of photovoltaic modules.

[0092] Specifically, by establishing an operating timeline, the periodic wear state of photovoltaic modules is predicted, and aging indicators corresponding to various characteristic indicators are established to eliminate the impact of normal wear on photovoltaic modules. At the same time, it can be determined whether the current photovoltaic modules have abnormal wear state, and the real-time health evaluation value can be corrected according to the judgment result, thereby improving the diagnostic accuracy of the health status of photovoltaic modules.

[0093] In a preferred embodiment of the present application, when a monitoring data packet is generated according to the operating parameters, it includes:

[0094] Obtain the real-time operating parameters of the photovoltaic components at the current feedback time node;

[0095] Extract the operating reference value of each characteristic indicator and establish an operating reference value sequence B, B = (b1, b2...bn), where bi is the operating reference value of the i-th characteristic indicator at the current feedback time node;

[0096] Obtain the real-time environment parameters and accumulated running time of the current feedback time node according to the real-time running parameters;

[0097] Generate environmental index tags based on real-time environmental parameters;

[0098] Generate duration index tags based on the accumulated running time;

[0099] Generate a monitoring data packet of the current feedback time node according to the operating reference value series B, the environment index tag and the duration index tag.

[0100] Specifically, when generating the health assessment value of a photovoltaic module, it includes:

[0101] Generate standard reference values ​​for each characteristic index based on the environmental index tags in the monitoring data package and all standard operating curves;

[0102] Establish a standard reference value sequence C, C = (c1, c2...cn); where ci is the standard reference value of the i-th characteristic indicator at the current feedback time node;

[0103] Generate the deviation evaluation value h of the current feedback time node according to the standard model;

[0104]

[0105] Among them, Q1 is the preset first fixed coefficient, βi is the fluctuation correction coefficient of the i-th characteristic indicator; αi is the influencing factor of the i-th characteristic indicator;

[0106] The health evaluation value g of the current feedback time node is set according to the deviation evaluation value h.

[0107] Specifically, the real-time environmental parameters are compared with the environmental conditions corresponding to the environmental index labels in the environmental disturbance curve, and the environmental conditions with the highest similarity are selected to generate the environmental index labels of the real-time environmental parameters.

[0108] Specifically, the standard reference values ​​corresponding to each characteristic indicator are quickly extracted according to the environmental index label, and a real-time deviation evaluation value is generated according to the preset standard model. The larger the deviation evaluation value, the greater the possibility of abnormal operation of the current photovoltaic component and the lower its health.

[0109] Specifically, when the health evaluation value g of the current feedback time node is set according to the deviation evaluation value h, it includes:

[0110] Presetting a first deviation evaluation value interval (H1, H2), a second deviation evaluation value interval (H2, H3) and a third deviation evaluation value interval (H3, H4);

[0111] If the deviation evaluation value h is within the preset first deviation evaluation value interval, the health evaluation value g=r / h is set, where r is the preset conversion coefficient;

[0112] If the deviation evaluation value h is within the preset second deviation evaluation value interval, a health evaluation value g is generated according to the expected aging model;

[0113] If the deviation evaluation value h is within the preset third deviation evaluation value interval, a first-level operation warning instruction is generated.

[0114] Specifically, the first-level operation warning instruction means that the current photovoltaic module is in a faulty state and needs to be inspected and repaired immediately to eliminate the fault in time to ensure the stable operation of the photovoltaic module.

[0115] In a preferred embodiment of the present application, when setting the fluctuation correction coefficient βi, it includes:

[0116] Set evaluation cycle and target characteristic indicators;

[0117] Generate the first-level monitoring values ​​of the target characteristic indicators at each feedback time node in the current evaluation cycle based on historical monitoring data;

[0118] Correct all primary monitoring values ​​of target characteristic indicators in the current evaluation period according to the environmental disturbance curve;

[0119] Generate secondary monitoring values ​​for each feedback time node in the current evaluation cycle based on the correction results;

[0120] Establish the secondary monitoring value series F, F = (f 1 , f 2 …f m ), where m is the number of feedback time nodes in the current evaluation cycle; fi is the secondary monitoring value of the target characteristic indicator at the i-th feedback time node;

[0121] Generate the fluctuation evaluation value k of the target characteristic index according to the secondary monitoring value series F;

[0122] The fluctuation correction coefficient β of the target characteristic index is set according to the fluctuation evaluation value k.

[0123] Specifically, when generating the fluctuation evaluation value k of the target characteristic index, it includes: k=e3*Q1* (f i -f') 2 ]+e4*Q2*[ (f i -f i-1 ) 2 ]; Among them, e3 is the preset third weight coefficient, e4 is the preset fourth weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; f' is the average value of all data in the secondary monitoring value series.

[0126] Specifically, by establishing an evaluation cycle, the fluctuation state of each characteristic indicator within a certain period is evaluated. The larger the fluctuation evaluation value, the more unstable the corresponding characteristic indicator is, the more likely it is that there will be short-term fluctuations, and the greater the possibility of failure risk. The corresponding fluctuation correction coefficient should also be larger.

[0127] Specifically, each evaluation index is normalized by presetting the third fixed coefficient and the fourth fixed coefficient so that they are in the same value range.

[0128] In a preferred embodiment of the present application, when generating a health evaluation value g according to an expected aging model, it includes:

[0129] Generate aging reference values ​​for each characteristic indicator based on the duration index tag and all aging curves in the monitoring data packet;

[0130] Establish an aging reference value sequence D, D = (d1, d2 ... dn), where di is the aging reference value of the i-th characteristic indicator at the current feedback time node;

[0131] The expected aging model generates a health assessment value g;

[0132]

[0133] Among them, e1 is the preset first weight coefficient, e2 is the preset second weight coefficient; αi is the influencing factor of the i-th characteristic indicator.

[0134] Specifically, the expected aging state of the current PV module is determined according to the duration index tag.

[0135] Specifically, the real-time health evaluation value of the PV module is corrected according to the cumulative operating time and expected aging model of the PV module to determine whether the PV module has abnormal loss problems, so that the health evaluation value can more accurately reflect the health status of the PV module.

[0136] Specifically, when judging whether to generate an operation warning instruction based on the health evaluation value, it includes:

[0137] Preset a first health evaluation value interval (G1, G2), a second health evaluation value interval (G2, G3) and a third health evaluation value interval (G3, G4);

[0138] If the health evaluation value g is within the preset first health evaluation value interval, the current feedback time node generates a first-level operation warning instruction;

[0139] If the health evaluation value g is within the preset second health evaluation value interval, the current feedback time node generates a second-level operation warning instruction;

[0140] If the health evaluation value g is within the preset third health evaluation value interval, no operation warning instruction is generated at the current feedback time node.

[0141] Specifically, when it is in the third health evaluation value range, it means that the photovoltaic module is in a healthy operating state. The second-level operation warning instruction means that the current photovoltaic module is in a sub-healthy state, that is, there is a risk of failure, and timely maintenance is required to eliminate the risk of failure and avoid affecting the operating efficiency of the photovoltaic module due to operational failures.

[0142] According to the first concept of the present application, multiple characteristic indicators are extracted based on historical operating parameters, and standard operating curves of each characteristic indicator are generated based on historical environmental parameters, and a standard model is established to eliminate environmental disturbances on the characteristic indicators, thereby improving the accuracy of evaluating the health status of photovoltaic modules.

[0143] According to the second concept of the present application, by establishing an expected aging model, when a photovoltaic module is in an abnormal state, the real-time health evaluation value of the photovoltaic module is corrected according to the cumulative operating time of the photovoltaic module and the expected aging model, so as to determine whether the photovoltaic module has abnormal loss problems, so that the health evaluation value can more accurately reflect the health status of the photovoltaic module, and the failure risk of the photovoltaic module can be repaired in time to ensure the stable operation of the photovoltaic module and increase the service life of the photovoltaic module.

[0144] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A method for diagnosing the health of a photovoltaic module, characterized in that: include: Generate multiple characteristic indicators based on PV module parameters, and establish standard models and expected aging models; Obtaining the operating parameters of the photovoltaic components according to the preset feedback time nodes, and generating a monitoring data packet according to the operating parameters; Generate health evaluation values ​​of PV modules based on monitoring data packets, standard models and expected aging models, and determine whether to generate operation warning instructions based on the health evaluation values; Among them, when generating multiple characteristic indicators, including: Establish a characteristic index sequence A, A = (a1, a2...an), where ai is the i-th characteristic index and n is the number of characteristic indicators.

2. The method for diagnosing the health of a photovoltaic module according to claim 1, characterized in that: When developing standard models and expected aging models, include: Obtain historical operating parameters and historical environmental parameters of photovoltaic modules; Select the target characteristic index according to the characteristic index sequence A; Generate an initial standard operating range of target characteristic indicators based on historical operating parameters; Generate environmental disturbance curves of target characteristic indicators based on historical environmental parameters; Generate a standard operating curve of the target characteristic index according to the environmental disturbance curve and the initial standard operating range; Establish a standard model based on the standard operating curves of all characteristic indicators; Establishing a running timeline; Generate an aging curve of target characteristic indicators based on the operation timeline and historical operation parameters; According to the aging curves of all characteristic indicators, an expected aging model is established.

3. The method for diagnosing the health of a photovoltaic module according to claim 2, characterized in that: When generating monitoring data packets based on operating parameters, it includes: Obtain the real-time operating parameters of the photovoltaic components at the current feedback time node; Extract the operating reference value of each characteristic indicator and establish an operating reference value sequence B, B = (b1, b2...bn), where bi is the operating reference value of the i-th characteristic indicator at the current feedback time node; Obtain the real-time environment parameters and accumulated running time of the current feedback time node according to the real-time running parameters; Generate environmental index tags based on real-time environmental parameters; Generate duration index tags based on the accumulated running time; Generate a monitoring data packet of the current feedback time node according to the operating reference value series B, the environment index tag and the duration index tag.

4. The method for diagnosing the health of a photovoltaic module according to claim 3, characterized in that: When generating the health assessment value of a PV module, it includes: Generate standard reference values ​​for each characteristic index based on the environmental index tags in the monitoring data package and all standard operating curves; Establish a standard reference value sequence C, C = (c1, c2...cn); where ci is the standard reference value of the i-th characteristic indicator at the current feedback time node; Generate the deviation evaluation value h of the current feedback time node according to the standard model; Among them, Q1 is the preset first fixed coefficient, βi is the fluctuation correction coefficient of the i-th characteristic indicator; αi is the influencing factor of the i-th characteristic indicator; The health evaluation value g of the current feedback time node is set according to the deviation evaluation value h.

5. The method for diagnosing the health of a photovoltaic module according to claim 4, characterized in that: When setting the fluctuation correction coefficient βi, include: Set evaluation cycle and target characteristic indicators; Generate the first-level monitoring values ​​of the target characteristic indicators at each feedback time node in the current evaluation cycle based on historical monitoring data; Correct all primary monitoring values ​​of target characteristic indicators in the current evaluation period according to the environmental disturbance curve; Generate secondary monitoring values ​​for each feedback time node in the current evaluation cycle based on the correction results; Establish a secondary monitoring value series F, F = (f1, f2…f m ), where m is the number of feedback time nodes in the current evaluation cycle; f i is the secondary monitoring value of the target characteristic indicator at the i-th feedback time node; Generate the fluctuation evaluation value k of the target characteristic index according to the secondary monitoring value series F; The fluctuation correction coefficient β of the target characteristic index is set according to the fluctuation evaluation value k.

6. The method for diagnosing the health of a photovoltaic module according to claim 5, characterized in that: When generating the fluctuation evaluation value k of the target characteristic index, it includes: k=e3*Q1* (f i -f') 2 ]+e4*Q2*[ (f i -f i-1 ) 2 ]; Among them, e3 is the preset third weight coefficient, e4 is the preset fourth weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; f' is the average value of all data in the secondary monitoring value series.

7. The method for diagnosing the health of a photovoltaic module according to claim 4, characterized in that: When the health evaluation value g of the current feedback time node is set according to the deviation evaluation value h, it includes: Presetting a first deviation evaluation value interval (H1, H2), a second deviation evaluation value interval (H2, H3) and a third deviation evaluation value interval (H3, H4); If the deviation evaluation value h is within the preset first deviation evaluation value interval, the health evaluation value g=r / h is set, where r is the preset conversion coefficient; If the deviation evaluation value h is within the preset second deviation evaluation value interval, a health evaluation value g is generated according to the expected aging model; If the deviation evaluation value h is within the preset third deviation evaluation value interval, a first-level operation warning instruction is generated.

8. The method for diagnosing the health of a photovoltaic module according to claim 7, characterized in that: When generating the health assessment value g according to the expected aging model, it includes: Generate aging reference values ​​for each characteristic indicator based on the duration index tag and all aging curves in the monitoring data packet; Establish an aging reference value sequence D, D = (d1, d2 ... dn), where di is the aging reference value of the i-th characteristic indicator at the current feedback time node; The expected aging model generates a health assessment value g; Among them, e1 is the preset first weight coefficient, e2 is the preset second weight coefficient; αi is the influencing factor of the i-th characteristic indicator.

9. The method for diagnosing the health of a photovoltaic module according to claim 8, characterized in that: When judging whether to generate an operation warning instruction based on the health evaluation value, it includes: Preset a first health evaluation value interval (G1, G2), a second health evaluation value interval (G2, G3) and a third health evaluation value interval (G3, G4); If the health evaluation value g is within the preset first health evaluation value interval, the current feedback time node generates a first-level operation warning instruction; If the health evaluation value g is within the preset second health evaluation value interval, the current feedback time node generates a second-level operation warning instruction; If the health evaluation value g is within the preset third health evaluation value interval, no operation warning instruction is generated at the current feedback time node.

Images